Openharness MCP Server

by philo-kim Your server? Claim it

local only

Openharness runs on your own machine — the client starts it, so there is no endpoint to ping. 36 installs a week from npm. Last commit 17 Mar 2026.

Lets AI coding agents discover and reference each other's recent sessions.

Installs per day peak 11 · avg 4 · +100% w/w

a month agotoday

Installs / week

npm · @freebird-ai/openharness

Stars

0 open issues

17 Mar 2026

Last commit

no releases in 90 days

MIT

License

TypeScript

Nothing serious here today

Today is the operative word: we check Openharness every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add openharness -- npx -y @freebird-ai/openharness

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "openharness": {
      "command": "npx",
      "args": [
        "-y",
        "@freebird-ai/openharness"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.openharness]
command = "npx"
args = ["-y", "@freebird-ai/openharness"]

.cursor/mcp.json

{
  "mcpServers": {
    "openharness": {
      "command": "npx",
      "args": [
        "-y",
        "@freebird-ai/openharness"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "openharness": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@freebird-ai/openharness"
      ]
    }
  }
}

Alternatives to Openharness

same job, measured the same way

Meshingly

by meshingly

End-to-end encrypted relay that lets AI coding sessions on different machines message each other.

474 installs/wk local only

Puenteo

by mano7onam

Let coding agents talk: search every agent session's history and message live sessions.

160 installs/wk local only

CacheBash

by feelgreatfoodie

Let your AI sessions talk to each other — messaging, tasks, sessions, and alerts

answering

Reagent Lab

by capybarist

Join a lab where AI agents from different people debate in turns and refute each other.

answering

agent-intercom

by iambashar

Lets Claude Code, Codex CLI and Antigravity message each other, with live push into open sessions.

101 installs/wk local only

Threadline MCP

by jkheadley

Agent-to-agent messaging relay. Discover agents, send messages, and receive replies. Zero-config.

210 installs/wk local only

hoptell

by eminuzun

Let AI coding agents (Claude Code, Codex, ...) message each other through a relay you host.

668 installs/wk local only

CogSession

by premanand8800

Session memory for AI coding agents: records decisions and dead ends, flags what went stale.

47 installs/wk local only

Openharness — questions

Answers built from our own checks of this server.

Why is there no uptime for Openharness?

Openharness runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the npm package @freebird-ai/openharness was installed 36 times last week.

How do I connect Openharness?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls @freebird-ai/openharness straight from npm; nothing to host, nothing to sign up for.

How many people use Openharness?

The npm package @freebird-ai/openharness was installed 36 times in the last week. Week over week that is +100%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Openharness open source?

Yes — it is published under the MIT licence, written in TypeScript and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.